Search

Purpose: To improve the precision of prescription duration estimates when using the reverse waiting time distribution (rWTD)., Methods: For each patient we uniformly sampled multiple random index dates within a sampling window of length δ . For each index date, we identified the last preceding prescription redemption, if any, within distance δ . Based on all pairs of last prescription and index date, we estimated prescription durations using the rWTD with robust variance estimation. In simulation studies with increasing misspecification we investigated bias, root mean square error (RMSE) and coverage probability of the rWTD using multiple index dates (1, 5, 10, and 20). We applied the method to Danish data on warfarin prescriptions from 2013 to 2014 stratifying by and adjusting for sex and age., Results: In simulation scenarios without misspecification, the relative bias was negligible (-0.04% to 0.01%) and nominal coverage probabilities almost retained (93.8%-95.4%). RMSE decreased with the number of random index dates (e.g., from 1.3 with 1 index date to 0.6 days with 5). With misspecification, the relative bias was higher irrespective of the number of index dates. Precision increased with the number of index dates, and hence coverage probabilities decreased. When estimating durations of warfarin prescriptions in Denmark, precision increased with number of index dates, in particular in strata with few patients (e.g., men 90+ years: width of 95% confidence interval was 16.2 days with 5 index dates versus 35.4 with 1)., Conclusions: Increasing the number of random index dates used with the rWTD improved precision without affecting bias., (© 2021 John Wiley & Sons Ltd.)

Purpose: A pervasive problem in registry-based pharmacoepidemiological studies is what exposure duration to assign to individual prescriptions. The parametric waiting time distribution (WTD) has been proposed as a method to estimate such durations. However, when prescription durations vary due to seasonal stockpiling, WTD estimates will vary with choice of index date. To counter this, we propose using random index dates., Methods: Within a calendar period of a given length, δ, we randomly sample individual index dates. We include the last prescription redemption prior to the index date in the analysis. Only redemptions within distance δ of the index date are included. In a simulation study with varying types and degrees of stockpiling at the end of the year, we investigated bias and precision of the reverse WTD with fixed and random index dates, respectively. In addition, we applied the new method to estimate durations of Norwegian warfarin prescriptions in 2014., Results: In simulation settings with stockpiling, the reverse WTD with random index dates had low relative biases (-0.65% to 6.64%) and high coverage probabilities (92.0% to 95.3%), although when stockpiling was pronounced, coverage probabilities decreased (2.7% to 85.8%). Using a fixed index date was inferior. The estimated duration of warfarin prescriptions in Norway using random index dates was 131 (130; 132) days., Conclusions: In the presence of seasonal stockpiling, the WTD with random index dates provides estimates of prescription durations, which are more stable, less biased and with better coverage when compared to using a fixed index date., (© 2020 John Wiley & Sons Ltd.)